© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 12255
    Prev
    Next
    INDEX
    Explanations

    ne

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StructEnd
    -1.02
     propOrder
    -0.81
     Мексичка
    -0.79
     BrowserModule
    -0.70
     PyLong
    -0.69
    AnimationsModule
    -0.69
    IndentedString
    -0.68
     HasFactory
    -0.67
     HttpNotFound
    -0.66
     للاسماء
    -0.65
    POSITIVE LOGITS
    mut
    0.51
    este
    0.43
     Nord
    0.43
     Arm
    0.41
    ja
    0.40
     mut
    0.40
     North
    0.40
    erv
    0.40
    nake
    0.40
    nu
    0.40
    Activations Density 0.016%

    No Known Activations